Can we avoid rounding-error estimation in HPC codes and still get trustworthy results? - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Can we avoid rounding-error estimation in HPC codes and still get trustworthy results?

Abstract

Numerical validation enables one to ensure the reliability of numerical computations that rely on floating-point operations. Discrete Stochastic Arithmetic (DSA) makes it possible to validate the accuracy of floating-point computations using random rounding. However, it may bring a large performance overhead compared with the standard floating-point operations. In this article, we show that with perturbed data it is possible to use standard floating-point arithmetic instead of DSA for the purpose of numerical validation. For instance, for codes including matrix multiplications, we can directly utilize the matrix multiplication routine (GEMM) of level-3 BLAS that is performed with standard floating-point arithmetic. Consequently, we can achieve a significant performance improvement by avoiding the performance overhead of DSA operations as well as by exploiting the speed of highly-optimized BLAS implementations. Finally, we demonstrate the performance gain using Intel MKL routines compared against the DSA version of BLAS routines.
Fichier principal
Vignette du fichier
NSV2020.pdf (329.28 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02925976 , version 1 (31-08-2020)

Identifiers

  • HAL Id : hal-02925976 , version 1

Cite

Fabienne Jézéquel, Stef Graillat, Daichi Mukunoki, Toshiyuki Imamura, Roman Iakymchuk. Can we avoid rounding-error estimation in HPC codes and still get trustworthy results?. NSV'20, 13th International Workshop on Numerical Software Verification, Jul 2020, Los Angeles, CA, United States. ⟨hal-02925976⟩
82 View
183 Download

Share

Gmail Facebook X LinkedIn More